oss-hunter

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and processes public GitHub content (see SKILL.md Phase 1/2 and bin/hunter.py calls to gh api search/repositories and gh issue list), which ingests untrusted, user-generated issue text that the agent analyzes to produce fix strategies and next actions, enabling indirect prompt injection risk.